Fix incorrect memory allocation by aligning element computation with tensor extents #5
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR fixes a segmentation fault that occurs during tensor memory allocation for large extents.
The issue stems from using the global extent array when computing elementsA, elementsB, and elementsC. While this works under the original toy example {6, 6, 6, 4, 4, 4}, it breaks when dimensions and mode mappings differ, as seen in configurations such as {1, 8, 512, 8, 512}.
The fix replaces usage of extent[...] with the corresponding per-tensor extents (extentA, extentB, and extentC), which are already calculated properly based on mode permutations. This ensures the memory allocation aligns with how the tensor descriptors are defined.
Tested using NVIDIA Grace with this repo